Upload all models and assets for bo (20251201)

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+visualizations/embedding_similarity.png filter=lfs diff=lfs merge=lfs -text
+visualizations/performance_dashboard.png filter=lfs diff=lfs merge=lfs -text
+visualizations/position_encoding_comparison.png filter=lfs diff=lfs merge=lfs -text
+visualizations/tsne_sentences.png filter=lfs diff=lfs merge=lfs -text
+visualizations/tsne_words.png filter=lfs diff=lfs merge=lfs -text
+visualizations/zipf_law.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,556 @@
+---
+language: bo
+language_name: BO
+language_family: tibetoburman_tibetic
+tags:
+  - wikilangs
+  - nlp
+  - tokenizer
+  - embeddings
+  - n-gram
+  - markov
+  - wikipedia
+  - monolingual
+  - family-tibetoburman_tibetic
+license: mit
+library_name: wikilangs
+pipeline_tag: feature-extraction
+datasets:
+  - omarkamali/wikipedia-monthly
+dataset_info:
+  name: wikipedia-monthly
+  description: Monthly snapshots of Wikipedia articles across 300+ languages
+metrics:
+  - name: best_compression_ratio
+    type: compression
+    value: 5.961
+  - name: best_isotropy
+    type: isotropy
+    value: 0.7739
+  - name: vocabulary_size
+    type: vocab
+    value: 13016
+generated: 2025-12-28
+---
+
+# BO - Wikilangs Models
+## Comprehensive Research Report & Full Ablation Study
+
+This repository contains NLP models trained and evaluated by Wikilangs, specifically on **BO** Wikipedia data.
+We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.
+
+## 📋 Repository Contents
+
+### Models & Assets
+
+- Tokenizers (8k, 16k, 32k, 64k)
+- N-gram models (2, 3, 4-gram)
+- Markov chains (context of 1, 2, 3 and 4)
+- Subword N-gram and Markov chains
+- Embeddings in various sizes and dimensions
+- Language Vocabulary
+- Language Statistics
+![Performance Dashboard](visualizations/performance_dashboard.png)
+
+### Analysis and Evaluation
+
+- [1. Tokenizer Evaluation](#1-tokenizer-evaluation)
+- [2. N-gram Model Evaluation](#2-n-gram-model-evaluation)
+- [3. Markov Chain Evaluation](#3-markov-chain-evaluation)
+- [4. Vocabulary Analysis](#4-vocabulary-analysis)
+- [5. Word Embeddings Evaluation](#5-word-embeddings-evaluation)
+- [6. Summary & Recommendations](#6-summary--recommendations)
+- [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
+- [Visualizations Index](#visualizations-index)
+
+---
+## 1. Tokenizer Evaluation
+
+![Tokenizer Compression](visualizations/tokenizer_compression.png)
+
+### Results
+
+| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens |
+|------------|-------------|---------------|----------|--------------|
+| **8k** | 4.296x | 4.23 | 0.3002% | 389,363 |
+| **16k** | 4.846x | 4.77 | 0.3387% | 345,182 |
+| **32k** | 5.407x | 5.33 | 0.3779% | 309,326 |
+| **64k** | 5.961x 🏆 | 5.87 | 0.4166% | 280,591 |
+
+### Tokenization Examples
+
+Below are sample sentences tokenized with each vocabulary size:
+
+**Sample 1:** `གསལ་བྱེད་སུམ་ཅུའི་ནང་ནས་ཀ་ག་བ་ཟ་ར་ས་དྲུག་ནི་ལ་བཏགས་ཅན་གྱི་ཡི་གེ་དྲུག་གོ།
+༼དུང་དཀ...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁གས ལ་བྱེད་ སུམ་ ཅུའི་ ནང་ནས་ ཀ་ ག ་བ་ ཟ་ ར་ ... (+16 more)` | 26 |
+| 16k | `▁གསལ་བྱེད་ སུམ་ཅུའི་ ནང་ནས་ ཀ་ ག ་བ་ ཟ་ ར་ ས་ དྲུག་ ... (+13 more)` | 23 |
+| 32k | `▁གསལ་བྱེད་ སུམ་ཅུའི་ ནང་ནས་ ཀ་ ག་བ་ ཟ་ ར་ས་ དྲུག་ནི་ ལ་བཏགས་ ཅན་གྱི་ ... (+9 more)` | 19 |
+| 64k | `▁གསལ་བྱེད་ སུམ་ཅུའི་ ནང་ནས་ ཀ་ ག་བ་ ཟ་ ར་ས་ དྲུག་ནི་ ལ་བཏགས་ ཅན་གྱི་ ... (+9 more)` | 19 |
+
+**Sample 2:** `བདག་སློབ་བུས་ལུས་ངག་ཡིད་གསུམ་ཁྱོད་ལ་དུས་བརྟན་དུ་འབུལ།   ང་ཚོ་མྱུར་དུ་མཇལ་འཛོམ་ཡང...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁བདག་ སློབ་བ ུས་ ལུས་ ངག་ཡིད་ གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ ... (+18 more)` | 28 |
+| 16k | `▁བདག་ སློབ་བ ུས་ ལུས་ངག་ཡིད་ གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ འབུལ། ... (+13 more)` | 23 |
+| 32k | `▁བདག་ སློབ་བ ུས་ ལུས་ངག་ཡིད་གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ འབུལ། ▁ང་ཚོ་ ... (+12 more)` | 22 |
+| 64k | `▁བདག་ སློབ་བ ུས་ ལུས་ངག་ཡིད་གསུམ་ ཁྱོད་ལ་ དུས་ བརྟན་ དུ་ འབུལ། ▁ང་ཚོ་ ... (+10 more)` | 20 |
+
+**Sample 3:** `མི་འཁྲུགས་པ་སྐྱབས་སྦྱིན་ཅན།   
+དེང་སང་ཇོ་བོ་རིན་པོ་ཆེའི་སྐུ་རྒྱབ་ཏུ་བཞུགས་པའི་ཇོ...`
+
+| Vocab | Tokens | Count |
+|-------|--------|-------|
+| 8k | `▁མི་ འཁྲུགས་ པ་ སྐྱབས་ སྦྱིན་ ཅན། ▁དེང་སང་ ��ོ་བོ་ རིན་པོ་ཆེའི་ སྐུ་ ... (+12 more)` | 22 |
+| 16k | `▁མི་ འཁྲུགས་ པ་ སྐྱབས་ སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་ སྐུ་ ... (+11 more)` | 21 |
+| 32k | `▁མི་ འཁྲུགས་པ་ སྐྱབས་ སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་ སྐུ་ རྒྱབ་ཏུ་བ ... (+7 more)` | 17 |
+| 64k | `▁མི་ འཁྲུགས་པ་ སྐྱབས་སྦྱིན་ ཅན། ▁དེང་སང་ ཇོ་བོ་ རིན་པོ་ཆེའི་སྐུ་ རྒྱབ་ཏུ་བ ཞུགས་པའི་ ཇོ་བོ་ ... (+5 more)` | 15 |
+
+
+### Key Findings
+
+- **Best Compression:** 64k achieves 5.961x compression
+- **Lowest UNK Rate:** 8k with 0.3002% unknown tokens
+- **Trade-off:** Larger vocabularies improve compression but increase model size
+- **Recommendation:** 32k vocabulary provides optimal balance for production use
+
+---
+## 2. N-gram Model Evaluation
+
+![N-gram Perplexity](visualizations/ngram_perplexity.png)
+
+![N-gram Coverage](visualizations/ngram_coverage.png)
+
+### Results
+
+| N-gram | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
+|--------|------------|---------|----------------|------------------|-------------------|
+| **2-gram** | 397 🏆 | 8.63 | 16,730 | 60.3% | 96.5% |
+| **2-gram** | 259 🏆 | 8.02 | 10,716 | 68.5% | 98.4% |
+| **3-gram** | 2,660 | 11.38 | 107,789 | 28.7% | 70.8% |
+| **3-gram** | 1,576 | 10.62 | 61,755 | 31.0% | 81.3% |
+| **4-gram** | 14,448 | 13.82 | 410,390 | 13.4% | 41.2% |
+| **4-gram** | 7,647 | 12.90 | 237,121 | 14.5% | 47.5% |
+
+### Top 5 N-grams by Size
+
+**2-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `ི ་` | 1,330,962 |
+| 2 | `་ ས` | 923,359 |
+| 3 | `ན ་` | 864,506 |
+| 4 | `ས ་` | 804,391 |
+| 5 | `་ ར` | 740,793 |
+
+**3-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `་ པ ་` | 412,050 |
+| 2 | `ྱ ི ་` | 279,592 |
+| 3 | `ོ ད ་` | 249,936 |
+| 4 | `་ དང ་` | 232,586 |
+| 5 | `་ ཀ ྱ` | 225,678 |
+
+**4-grams:**
+
+| Rank | N-gram | Count |
+|------|--------|-------|
+| 1 | `་ པའ ི ་` | 220,243 |
+| 2 | `་ ཀ ྱ ི` | 185,475 |
+| 3 | `་ ར ྒ ྱ` | 176,176 |
+| 4 | `ཀ ྱ ི ་` | 145,131 |
+| 5 | `་ ད ུ ་` | 133,021 |
+
+
+### Key Findings
+
+- **Best Perplexity:** 2-gram with 259
+- **Entropy Trend:** Decreases with larger n-grams (more predictable)
+- **Coverage:** Top-1000 patterns cover ~47% of corpus
+- **Recommendation:** 4-gram or 5-gram for best predictive performance
+
+---
+## 3. Markov Chain Evaluation
+
+![Markov Entropy](visualizations/markov_entropy.png)
+
+![Markov Branching](visualizations/markov_branching.png)
+
+### Results
+
+| Context | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
+|---------|-------------|------------|------------------|-----------------|----------------|
+| **1** | 0.2954 | 1.227 | 3.27 | 41,503 | 70.5% |
+| **1** | 1.4785 | 2.787 | 10.14 | 4,527 | 0.0% |
+| **2** | 0.2647 🏆 | 1.201 | 2.76 | 135,576 | 73.5% |
+| **2** | 0.6082 🏆 | 1.524 | 3.67 | 45,909 | 39.2% |
+| **3** | 0.2919 | 1.224 | 2.37 | 373,945 | 70.8% |
+| **3** | 0.5729 | 1.488 | 2.90 | 168,571 | 42.7% |
+| **4** | 0.3575 | 1.281 | 2.36 | 884,085 | 64.2% |
+| **4** | 0.4734 | 1.388 | 2.39 | 489,183 | 52.7% |
+
+### Generated Text Samples
+
+Below are text samples generated from each Markov chain model:
+
+**Context Size 1:**
+
+1. `་ བ ། ཉམས ་ ན ་ འག ྲ ག ་ མ ་ ཤ ུ ང`
+2. `ི ར ྐ ྱ ན ་ བས ྒ ྲ ི ་ ད ་ མ ་ གཅ`
+3. `ོ ས ྙ ི ་ དང ་ ས ྲ ི ས ་ ཆ ུ ར ུ`
+
+**Context Size 2:**
+
+1. `ི ་ ས ྒ ྲ ོ ད [ ང ] པའ ི ་ དཀར ་ ཡ ི`
+2. `་ ས ླ ོ ང ་ ག ྱ ི ས ་ འབ ྱ ོ ན ་ བཅས`
+3. `ན ་ ཆ ོ ས ་ རབ ་ འབ ྱ ུ ར ། ། ཁ ོ ངས`
+
+**Context Size 3:**
+
+1. `་ པ ་ ཆ ུ བ ་ བ ྱ ེ ད ། ། ཁ ྲ ་ བ ྱ`
+2. `ྱ ི ་ ཕ ་ ར ོ ལ ་ ར ླ བས ་ ཀ ྱ ི ་ ར`
+3. `ོ ད ་ ཀ ྱ ི ས ་ བད ུ ན ་ ཅ ི ་ མ ི ན`
+
+**Context Size 4:**
+
+1. `་ པའ ི ་ ར ྒ ྱ ར ་ བར ་ དཀའ ་ བའ ི ་ འཕ ྲ ུ`
+2. `་ ཀ ྱ ི ་ ནང ་ ག ི ་ འབ ུ མ ་ ཡང ་ ། ། ཤ`
+3. `་ ར ྒ ྱ ུ ད ་ པ ། ད ེ ་ ས ྟ ེ ། བ ྲ མ`
+
+
+### Key Findings
+
+- **Best Predictability:** Context-2 with 73.5% predictability
+- **Branching Factor:** Decreases with context size (more deterministic)
+- **Memory Trade-off:** Larger contexts require more storage (489,183 contexts)
+- **Recommendation:** Context-3 or Context-4 for text generation
+
+---
+## 4. Vocabulary Analysis
+
+![Zipf's Law](visualizations/zipf_law.png)
+
+![Top Words](visualizations/top20_words.png)
+
+![Coverage Curve](visualizations/vocab_coverage.png)
+
+### Statistics
+
+| Metric | Value |
+|--------|-------|
+| Vocabulary Size | 13,016 |
+| Total Tokens | 18,343,262 |
+| Mean Frequency | 1409.29 |
+| Median Frequency | 3 |
+| Frequency Std Dev | 31347.07 |
+
+### Most Common Words
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | ས | 1,859,452 |
+| 2 | ར | 1,242,082 |
+| 3 | ད | 1,225,016 |
+| 4 | ན | 1,119,190 |
+| 5 | ག | 979,844 |
+| 6 | ལ | 962,286 |
+| 7 | བ | 831,513 |
+| 8 | ང | 704,629 |
+| 9 | མ | 647,161 |
+| 10 | པ | 638,483 |
+
+### Least Common Words (from vocabulary)
+
+| Rank | Word | Frequency |
+|------|------|-----------|
+| 1 | ༡༡༦༠ | 2 |
+| 2 | w1kg9520 | 2 |
+| 3 | jayasena | 2 |
+| 4 | ༡༡ཙམ | 2 |
+| 5 | 252591 | 2 |
+| 6 | 2525b4 | 2 |
+| 7 | 2525b2 | 2 |
+| 8 | caryā | 2 |
+| 9 | gīti | 2 |
+| 10 | caryāgītivṛtti | 2 |
+
+### Zipf's Law Analysis
+
+| Metric | Value |
+|--------|-------|
+| Zipf Coefficient | 1.8006 |
+| R² (Goodness of Fit) | 0.975288 |
+| Adherence Quality | **excellent** |
+
+### Coverage Analysis
+
+| Top N Words | Coverage |
+|-------------|----------|
+| Top 100 | 92.9% |
+| Top 1,000 | 99.6% |
+| Top 5,000 | 99.9% |
+| Top 10,000 | 100.0% |
+
+### Key Findings
+
+- **Zipf Compliance:** R²=0.9753 indicates excellent adherence to Zipf's law
+- **High Frequency Dominance:** Top 100 words cover 92.9% of corpus
+- **Long Tail:** 3,016 words needed for remaining 0.0% coverage
+
+---
+## 5. Word Embeddings Evaluation
+
+![Embedding Isotropy](visualizations/embedding_isotropy.png)
+
+![Similarity Matrix](visualizations/embedding_similarity.png)
+
+![t-SNE Words](visualizations/tsne_words.png)
+
+![t-SNE Sentences](visualizations/tsne_sentences.png)
+
+### Model Comparison
+
+| Model | Vocab Size | Dimension | Avg Norm | Std Norm | Isotropy |
+|-------|------------|-----------|----------|----------|----------|
+| **mono_32d** | 8,661 | 32 | 6.077 | 1.370 | 0.7739 🏆 |
+| **mono_64d** | 8,661 | 64 | 6.426 | 1.018 | 0.7102 |
+| **mono_128d** | 8,661 | 128 | 6.678 | 0.842 | 0.5344 |
+| **embeddings_enhanced** | 0 | 0 | 0.000 | 0.000 | 0.0000 |
+
+### Key Findings
+
+- **Best Isotropy:** mono_32d with 0.7739 (more uniform distribution)
+- **Dimension Trade-off:** Higher dimensions capture more semantics but reduce isotropy
+- **Vocabulary Coverage:** All models cover 8,661 words
+- **Recommendation:** 100d for balanced semantic capture and efficiency
+
+---
+## 6. Summary & Recommendations
+
+![Performance Dashboard](visualizations/performance_dashboard.png)
+
+### Production Recommendations
+
+| Component | Recommended | Rationale |
+|-----------|-------------|-----------|
+| Tokenizer | **32k BPE** | Best compression (5.96x) with low UNK rate |
+| N-gram | **5-gram** | Lowest perplexity (259) |
+| Markov | **Context-4** | Highest predictability (73.5%) |
+| Embeddings | **100d** | Balanced semantic capture and isotropy |
+
+---
+## Appendix: Metrics Glossary & Interpretation Guide
+
+This section provides definitions, intuitions, and guidance for interpreting the metrics used throughout this report.
+
+### Tokenizer Metrics
+
+**Compression Ratio**
+> *Definition:* The ratio of characters to tokens (chars/token). Measures how efficiently the tokenizer represents text.
+>
+> *Intuition:* Higher compression means fewer tokens needed to represent the same text, reducing sequence lengths for downstream models. A 3x compression means ~3 characters per token on average.
+>
+> *What to seek:* Higher is generally better for efficiency, but extremely high compression may indicate overly aggressive merging that loses morphological information.
+
+**Average Token Length (Fertility)**
+> *Definition:* Mean number of characters per token produced by the tokenizer.
+>
+> *Intuition:* Reflects the granularity of tokenization. Longer tokens capture more context but may struggle with rare words; shorter tokens are more flexible but increase sequence length.
+>
+> *What to seek:* Balance between 2-5 characters for most languages. Arabic/morphologically-rich languages may benefit from slightly longer tokens.
+
+**Unknown Token Rate (OOV Rate)**
+> *Definition:* Percentage of tokens that map to the unknown/UNK token, indicating words the tokenizer cannot represent.
+>
+> *Intuition:* Lower OOV means better vocabulary coverage. High OOV indicates the tokenizer encounters many unseen character sequences.
+>
+> *What to seek:* Below 1% is excellent; below 5% is acceptable. BPE tokenizers typically achieve very low OOV due to subword fallback.
+
+### N-gram Model Metrics
+
+**Perplexity**
+> *Definition:* Measures how "surprised" the model is by test data. Mathematically: 2^(cross-entropy). Lower values indicate better prediction.
+>
+> *Intuition:* If perplexity is 100, the model is as uncertain as if choosing uniformly among 100 options at each step. A perplexity of 10 means effectively choosing among 10 equally likely options.
+>
+> *What to seek:* Lower is better. Perplexity decreases with larger n-grams (more context). Values vary widely by language and corpus size.
+
+**Entropy**
+> *Definition:* Average information content (in bits) needed to encode the next token given the context. Related to perplexity: perplexity = 2^entropy.
+>
+> *Intuition:* High entropy means high uncertainty/randomness; low entropy means predictable patterns. Natural language typically has entropy between 1-4 bits per character.
+>
+> *What to seek:* Lower entropy indicates more predictable text patterns. Entropy should decrease as n-gram size increases.
+
+**Coverage (Top-K)**
+> *Definition:* Percentage of corpus occurrences explained by the top K most frequent n-grams.
+>
+> *Intuition:* High coverage with few patterns indicates repetitive/formulaic text; low coverage suggests diverse vocabulary usage.
+>
+> *What to seek:* Depends on use case. For language modeling, moderate coverage (40-60% with top-1000) is typical for natural text.
+
+### Markov Chain Metrics
+
+**Average Entropy**
+> *Definition:* Mean entropy across all contexts, measuring average uncertainty in next-word prediction.
+>
+> *Intuition:* Lower entropy means the model is more confident about what comes next. Context-1 has high entropy (many possible next words); Context-4 has low entropy (few likely continuations).
+>
+> *What to seek:* Decreasing entropy with larger context sizes. Very low entropy (<0.1) indicates highly deterministic transitions.
+
+**Branching Factor**
+> *Definition:* Average number of unique next tokens observed for each context.
+>
+> *Intuition:* High branching = many possible continuations (flexible but uncertain); low branching = few options (predictable but potentially repetitive).
+>
+> *What to seek:* Branching factor should decrease with context size. Values near 1.0 indicate nearly deterministic chains.
+
+**Predictability**
+> *Definition:* Derived metric: (1 - normalized_entropy) × 100%. Indicates how deterministic the model's predictions are.
+>
+> *Intuition:* 100% predictability means the next word is always certain; 0% means completely random. Real text falls between these extremes.
+>
+> *What to seek:* Higher predictability for text generation quality, but too high (>98%) may produce repetitive output.
+
+### Vocabulary & Zipf's Law Metrics
+
+**Zipf's Coefficient**
+> *Definition:* The slope of the log-log plot of word frequency vs. rank. Zipf's law predicts this should be approximately -1.
+>
+> *Intuition:* A coefficient near -1 indicates the corpus follows natural language patterns where a few words are very common and most words are rare.
+>
+> *What to seek:* Values between -0.8 and -1.2 indicate healthy natural language distribution. Deviations may suggest domain-specific or artificial text.
+
+**R² (Coefficient of Determination)**
+> *Definition:* Measures how well the linear fit explains the frequency-rank relationship. Ranges from 0 to 1.
+>
+> *Intuition:* R² near 1.0 means the data closely follows Zipf's law; lower values indicate deviation from expected word frequency patterns.
+>
+> *What to seek:* R² > 0.95 is excellent; > 0.99 indicates near-perfect Zipf adherence typical of large natural corpora.
+
+**Vocabulary Coverage**
+> *Definition:* Cumulative percentage of corpus tokens accounted for by the top N words.
+>
+> *Intuition:* Shows how concentrated word usage is. If top-100 words cover 50% of text, the corpus relies heavily on common words.
+>
+> *What to seek:* Top-100 covering 30-50% is typical. Higher coverage indicates more repetitive text; lower suggests richer vocabulary.
+
+### Word Embedding Metrics
+
+**Isotropy**
+> *Definition:* Measures how uniformly distributed vectors are in the embedding space. Computed as the ratio of minimum to maximum singular values.
+>
+> *Intuition:* High isotropy (near 1.0) means vectors spread evenly in all directions; low isotropy means vectors cluster in certain directions, reducing expressiveness.
+>
+> *What to seek:* Higher isotropy generally indicates better-quality embeddings. Values > 0.1 are reasonable; > 0.3 is good. Lower-dimensional embeddings tend to have higher isotropy.
+
+**Average Norm**
+> *Definition:* Mean magnitude (L2 norm) of word vectors in the embedding space.
+>
+> *Intuition:* Indicates the typical "length" of vectors. Consistent norms suggest stable training; high variance may indicate some words are undertrained.
+>
+> *What to seek:* Relatively consistent norms across models. The absolute value matters less than consistency (low std deviation).
+
+**Cosine Similarity**
+> *Definition:* Measures angular similarity between vectors, ranging from -1 (opposite) to 1 (identical direction).
+>
+> *Intuition:* Words with similar meanings should have high cosine similarity. This is the standard metric for semantic relatedness in embeddings.
+>
+> *What to seek:* Semantically related words should score > 0.5; unrelated words should be near 0. Synonyms often score > 0.7.
+
+**t-SNE Visualization**
+> *Definition:* t-Distributed Stochastic Neighbor Embedding - a dimensionality reduction technique that preserves local structure for visualization.
+>
+> *Intuition:* Clusters in t-SNE plots indicate groups of semantically related words. Spread indicates vocabulary diversity; tight clusters suggest semantic coherence.
+>
+> *What to seek:* Meaningful clusters (e.g., numbers together, verbs together). Avoid over-interpreting distances - t-SNE preserves local, not global, structure.
+
+### General Interpretation Guidelines
+
+1. **Compare within model families:** Metrics are most meaningful when comparing models of the same type (e.g., 8k vs 64k tokenizer).
+2. **Consider trade-offs:** Better performance on one metric often comes at the cost of another (e.g., compression vs. OOV rate).
+3. **Context matters:** Optimal values depend on downstream tasks. Text generation may prioritize different metrics than classification.
+4. **Corpus influence:** All metrics are influenced by corpus characteristics. Wikipedia text differs from social media or literature.
+5. **Language-specific patterns:** Morphologically rich languages (like Arabic) may show different optimal ranges than analytic languages.
+
+
+### Visualizations Index
+
+| Visualization | Description |
+|---------------|-------------|
+| Tokenizer Compression | Compression ratios by vocabulary size |
+| Tokenizer Fertility | Average token length by vocabulary |
+| Tokenizer OOV | Unknown token rates |
+| Tokenizer Total Tokens | Total tokens by vocabulary |
+| N-gram Perplexity | Perplexity by n-gram size |
+| N-gram Entropy | Entropy by n-gram size |
+| N-gram Coverage | Top pattern coverage |
+| N-gram Unique | Unique n-gram counts |
+| Markov Entropy | Entropy by context size |
+| Markov Branching | Branching factor by context |
+| Markov Contexts | Unique context counts |
+| Zipf's Law | Frequency-rank distribution with fit |
+| Vocab Frequency | Word frequency distribution |
+| Top 20 Words | Most frequent words |
+| Vocab Coverage | Cumulative coverage curve |
+| Embedding Isotropy | Vector space uniformity |
+| Embedding Norms | Vector magnitude distribution |
+| Embedding Similarity | Word similarity heatmap |
+| Nearest Neighbors | Similar words for key terms |
+| t-SNE Words | 2D word embedding visualization |
+| t-SNE Sentences | 2D sentence embedding visualization |
+| Position Encoding | Encoding method comparison |
+| Model Sizes | Storage requirements |
+| Performance Dashboard | Comprehensive performance overview |
+
+---
+## About This Project
+
+### Data Source
+
+Models trained on [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly) - a monthly snapshot of Wikipedia articles across 300+ languages.
+
+### Project
+
+A project by **[Wikilangs](https://wikilangs.org)** - Open-source NLP models for every Wikipedia language.
+
+### Maintainer
+
+[Omar Kamali](https://omarkamali.com) - [Omneity Labs](https://omneitylabs.com)
+
+### Citation
+
+If you use these models in your research, please cite:
+
+```bibtex
+@misc{wikilangs2025,
+  author = {Kamali, Omar},
+  title = {Wikilangs: Open NLP Models for Wikipedia Languages},
+  year = {2025},
+  publisher = {HuggingFace},
+  url = {https://huggingface.co/wikilangs}
+  institution = {Omneity Labs}
+}
+```
+
+### License
+
+MIT License - Free for academic and commercial use.
+
+### Links
+
+- 🌐 Website: [wikilangs.org](https://wikilangs.org)
+- 🤗 Models: [huggingface.co/wikilangs](https://huggingface.co/wikilangs)
+- 📊 Data: [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly)
+- 👤 Author: [Omar Kamali](https://huggingface.co/omarkamali)
+---
+*Generated by Wikilangs Models Pipeline*
+
+*Report Date: 2025-12-28 07:45:49*

models/embeddings/monolingual/bo_128d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d28fd32d66a933b9d54910c53ae79e731552039f72a158a509f33345be938c
+size 1033296964

models/embeddings/monolingual/bo_128d.meta.json

@@ -0,0 +1 @@
+{"lang": "bo", "dim": 128, "max_seq_len": 512, "is_aligned": false}

models/embeddings/monolingual/bo_128d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "bo",
+  "dimension": 128,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 128,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 8661
+}

models/embeddings/monolingual/bo_32d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7ec38e53b69d6fe0c7bf028ecf260182dc2c464b0a3998b36285dcdcd0d790
+size 258645316

models/embeddings/monolingual/bo_32d.meta.json

@@ -0,0 +1 @@
+{"lang": "bo", "dim": 32, "max_seq_len": 512, "is_aligned": false}

models/embeddings/monolingual/bo_32d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "bo",
+  "dimension": 32,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 32,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 8661
+}

models/embeddings/monolingual/bo_64d.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a39136f57bc0193b521701d5895d97332f84bef7738e48d579bf3e941611efb
+size 516862532

models/embeddings/monolingual/bo_64d.meta.json

@@ -0,0 +1 @@
+{"lang": "bo", "dim": 64, "max_seq_len": 512, "is_aligned": false}

models/embeddings/monolingual/bo_64d_metadata.json

@@ -0,0 +1,13 @@
+{
+  "language": "bo",
+  "dimension": 64,
+  "version": "monolingual",
+  "training_params": {
+    "dim": 64,
+    "min_count": 5,
+    "window": 5,
+    "negative": 5,
+    "epochs": 5
+  },
+  "vocab_size": 8661
+}

models/subword_markov/bo_markov_ctx1_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6b72dd2f3cb1ce71f886ce79e1991ebc9d866ba3d8e9a4e0765a566abef832
+size 295033

models/subword_markov/bo_markov_ctx1_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "subword",
+  "language": "bo",
+  "unique_contexts": 4527,
+  "total_transitions": 51775331
+}

models/subword_markov/bo_markov_ctx2_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1343c1704ab694d0457b93b45cf4513b9cc61d7f7b379f22055ad12bdb3453f7
+size 1399204

models/subword_markov/bo_markov_ctx2_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "subword",
+  "language": "bo",
+  "unique_contexts": 45909,
+  "total_transitions": 51761048
+}

models/subword_markov/bo_markov_ctx3_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238ba3561b2e3bbe4353470450e8e2a855ebb948f45a77fec280ddd79e71a6a7
+size 4147532

models/subword_markov/bo_markov_ctx3_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "subword",
+  "language": "bo",
+  "unique_contexts": 168571,
+  "total_transitions": 51746765
+}

models/subword_markov/bo_markov_ctx4_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350c4223d741dac9f5df6b518504739dec14c750eeba2ee92fbe4f3e7793abd0
+size 11386093

models/subword_markov/bo_markov_ctx4_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "subword",
+  "language": "bo",
+  "unique_contexts": 489183,
+  "total_transitions": 51732482
+}

models/subword_ngram/bo_2gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63fe48d7e16314165daac5a09388e1993a92697e7057f3ca8766f9e8eccfe1e
+size 139446

models/subword_ngram/bo_2gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "subword",
+  "language": "bo",
+  "unique_ngrams": 10716,
+  "total_ngrams": 51775331
+}

models/subword_ngram/bo_3gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db32beee277ce5b96116ccb7fcb3a4f8100711767d8803de99225390f28611b6
+size 784140

models/subword_ngram/bo_3gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "subword",
+  "language": "bo",
+  "unique_ngrams": 61755,
+  "total_ngrams": 51761048
+}

models/subword_ngram/bo_4gram_subword.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dfa2e76430d6ce1f681949cc2acbe14cc49ddf452d17256204e4387b0a24cc6
+size 2949767

models/subword_ngram/bo_4gram_subword_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "subword",
+  "language": "bo",
+  "unique_ngrams": 237121,
+  "total_ngrams": 51746765
+}

models/tokenizer/bo_tokenizer_16k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab010daa62bc41c1b8032f9d748af4fd37db53dee73a43da0d904f4823dd00e
+size 703550

models/tokenizer/bo_tokenizer_32k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f36be3bd4045efa166c3cb5f777437692dfa9587f1e56e7fbb3e723de6eba9
+size 1237082

models/tokenizer/bo_tokenizer_64k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c954964333d2da25bea610a3945473fa0588b9e1f80593834b369fdb080402a0
+size 2362449

models/tokenizer/bo_tokenizer_8k.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea17dc7300f482ce3d9c095d25a6131c7ed3dd8f32ff3049fea997cc38cbb782
+size 454260

models/vocabulary/bo_vocabulary.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eeece097f87af2ab0ce9e55f44cb872a6e4f828118a6c10d018670e7b075bbb
+size 213596

models/vocabulary/bo_vocabulary_metadata.json

@@ -0,0 +1,16 @@
+{
+  "language": "bo",
+  "vocabulary_size": 13016,
+  "statistics": {
+    "type_token_ratio": 0.0022376683701338307,
+    "coverage": {
+      "top_100": 0.9279372697332342,
+      "top_1000": 0.9940718580638173,
+      "top_5000": 0.9973993752774359,
+      "top_10000": 0.9981424886732634
+    },
+    "hapax_count": 28093,
+    "hapax_ratio": 0.6833783356442629,
+    "total_documents": 14283
+  }
+}

models/word_markov/bo_markov_ctx1_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a4478f179efe4762715a399df064c2175ac4508700aa5231ca3f2241d9baa8
+size 1444473

models/word_markov/bo_markov_ctx1_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 1,
+  "variant": "word",
+  "language": "bo",
+  "unique_contexts": 41503,
+  "total_transitions": 43169277
+}

models/word_markov/bo_markov_ctx2_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f391dd5db47185870344cb2760e2499b029b58579a143fa623dcb9747232575
+size 3531426

models/word_markov/bo_markov_ctx2_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 2,
+  "variant": "word",
+  "language": "bo",
+  "unique_contexts": 135576,
+  "total_transitions": 43154994
+}

models/word_markov/bo_markov_ctx3_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed95c18ea1ad5d5136b568a6334b628dd4b3b1e75fc8e5b4f09af2322d1f4d2
+size 9151444

models/word_markov/bo_markov_ctx3_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 3,
+  "variant": "word",
+  "language": "bo",
+  "unique_contexts": 373945,
+  "total_transitions": 43140711
+}

models/word_markov/bo_markov_ctx4_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7238c4b068f37f9deb6d6f25e25cd27d86fbecff6228c94b188cb8f861f7f7c
+size 22175465

models/word_markov/bo_markov_ctx4_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "context_size": 4,
+  "variant": "word",
+  "language": "bo",
+  "unique_contexts": 884085,
+  "total_transitions": 43126429
+}

models/word_ngram/bo_2gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b0fcbc93bc920804d2780f7b1ac6cc27c0d8317fc2680aa979f081e0f102a1
+size 240285

models/word_ngram/bo_2gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 2,
+  "variant": "word",
+  "language": "bo",
+  "unique_ngrams": 16730,
+  "total_ngrams": 43169277
+}

models/word_ngram/bo_3gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71ca878d82f6d8e0a1f3f01aa1350846d2870fdadfca3da38183eb64306aa9b
+size 1495235

models/word_ngram/bo_3gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 3,
+  "variant": "word",
+  "language": "bo",
+  "unique_ngrams": 107789,
+  "total_ngrams": 43154994
+}

models/word_ngram/bo_4gram_word.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c6d114cdab9167d30db5263ec4923cc3598ee22259e5e41b51e2a9f26d24919
+size 5818114

models/word_ngram/bo_4gram_word_metadata.json

@@ -0,0 +1,7 @@
+{
+  "n": 4,
+  "variant": "word",
+  "language": "bo",
+  "unique_ngrams": 410390,
+  "total_ngrams": 43140711
+}